- Twitch: keep stale message-handler cleanup callbacks from removing newer handler registrations for the same account, preserving inbound message delivery after reconnects. Fixes #83888. (#85425) Thanks @alkor2000.

- Memory/LanceDB: expose public memory artifacts through the active memory provider bridge so memory-wiki imports durable memory files, daily notes, dream reports, and event logs without depending on memory-core internals. Fixes #83604. (#85060) Thanks @brokemac79.

- Crabbox: keep AWS hydration compatible with local Actions replay by inlining the hydrate workflow's Node/pnpm setup instead of invoking repo-local composite actions.

- Agents/subagents: simplify native sub-agent completion handoff so children report their latest visible assistant result to the requester without using `message`, while keeping parent-owned message-tool delivery policy intact. Fixes #85070. (#85089) Thanks @brokemac79.

- Docker setup: stop printing the Gateway bearer token in setup logs and printed follow-up commands.

- Agents: let embedded compaction fallback retries proceed when PI-compatible candidates do not need agent harness plugin preparation.

- Agents/tools: honor configured custom provider API keys when deciding whether media, image-generation, video-generation, music-generation, and PDF tools are available. (#85570)

public let internalevents: [[String: AnyCodable]]?

public let inputprovenance: [String: AnyCodable]?

public let sourcereplydeliverymode: AnyCodable?

public let disablemessagetool: Bool?

public let voicewaketrigger: String?

public let idempotencykey: String

public let label: String?

internalevents: [[String: AnyCodable]]?,

inputprovenance: [String: AnyCodable]?,

sourcereplydeliverymode: AnyCodable?,

disablemessagetool: Bool?,

voicewaketrigger: String?,

idempotencykey: String,

label: String?)

self.internalevents = internalevents

self.inputprovenance = inputprovenance

self.sourcereplydeliverymode = sourcereplydeliverymode

self.disablemessagetool = disablemessagetool

self.voicewaketrigger = voicewaketrigger

self.idempotencykey = idempotencykey

self.label = label

case internalevents = "internalEvents"

case inputprovenance = "inputProvenance"

case sourcereplydeliverymode = "sourceReplyDeliveryMode"

case disablemessagetool = "disableMessageTool"

case voicewaketrigger = "voiceWakeTrigger"

case idempotencykey = "idempotencyKey"

case label

- Subagent completion best-effort closes tracked browser tabs/processes for the child session before announce cleanup continues.

- Isolated cron completion best-effort closes tracked browser tabs/processes for the cron session before the run fully tears down.

- Isolated cron delivery waits out descendant subagent follow-up when needed and suppresses stale parent acknowledgement text instead of announcing it.

- Subagent completion delivery prefers the latest visible assistant text; if that is empty it falls back to sanitized latest tool/toolResult text, and timeout-only tool-call runs can collapse to a short partial-progress summary. Terminal failed runs announce failure status without replaying captured reply text.

- Subagent completion delivery uses the child's latest visible assistant text only. Tool/toolResult output is not promoted into child result text. Terminal failed runs announce failure status without replaying captured reply text.

- Cleanup failures do not mask the real task outcome.

When applying maintenance, OpenClaw also removes stale `cron:<jobId>:run:<uuid>` session registry rows older than 7 days, while preserving rows for currently running cron jobs and leaving non-cron session rows untouched.

read_when:

- You want to understand what session tools the agent has

- You want to configure cross-session access or sub-agent spawning

- You want to inspect status or control spawned sub-agents

- You want to inspect spawned sub-agent status

title: "Session tools"

---

| `sessions_send` | Send a message to another session and optionally wait |

| `sessions_spawn` | Spawn an isolated sub-agent session for background work |

| `sessions_yield` | End the current turn and wait for follow-up sub-agent results |

| `subagents` | List, steer, or kill spawned sub-agents for this session |

| `subagents` | List spawned sub-agent status for this session |

| `session_status` | Show a `/status`-style card and optionally set a per-session model override |

These tools are still subject to the active tool profile and allow/deny

you want completion results to arrive as the next message instead of building

poll loops.

`subagents` is the control-plane helper for already spawned OpenClaw

sub-agents. It supports:

- `action: "list"` to inspect active/recent runs

- `action: "steer"` to send follow-up guidance to a running child

- `action: "kill"` to stop one child or `all`

`subagents` is the visibility helper for already spawned OpenClaw

sub-agents. It supports `action: "list"` to inspect active/recent runs.

## Spawning sub-agents

- If neither a bound route nor a usable stored route exists, direct delivery can fail and the result falls back to queued session delivery instead of posting immediately to chat.

- Invalid or stale targets can still force queue fallback or final delivery failure.

- If the child's last visible assistant reply is the exact silent token `NO_REPLY` / `no_reply`, or exactly `ANNOUNCE_SKIP`, OpenClaw intentionally suppresses the announce instead of posting stale earlier progress.

- If the child timed out after only tool calls, the announce can collapse that into a short partial-progress summary instead of replaying raw tool output.

- Tool/toolResult output is not promoted into child result text; the result is the child's latest visible assistant reply.

Debug:

`bundle-mcp` tools while `minimal` and `tools.deny: ["bundle-mcp"]` filter them.

`test:docker:cron-mcp-cleanup` is deterministic and does not need a live model

key. It starts a seeded Gateway with a real stdio MCP probe server, runs an

isolated cron turn and a `/subagents spawn` one-shot child turn, then verifies

isolated cron turn and a `sessions_spawn` one-shot child turn, then verifies

the MCP child process exits after each run.

Manual ACP plain-language thread smoke (not CI):

</Accordion>

<Accordion title="Subagents and ACP">

- `/subagents list|kill|log|info|send|steer|spawn` manages sub-agent runs for the current session.

- `/subagents list|log|info` inspects sub-agent runs for the current session.

- `/acp spawn|cancel|steer|close|sessions|status|set-mode|set|cwd|permissions|timeout|model|reset-options|doctor|install|help` manages ACP sessions and runtime options.

- `/focus <target>` binds the current Discord thread or Telegram topic/conversation to a session target.

- `/unfocus` removes the current binding.

- `/agents` lists thread-bound agents for the current session.

- `/kill <id|#|all>` aborts one or all running sub-agents.

- `/subagents steer <id|#> <message>` sends steering to a running sub-agent. See [Steer](/tools/steer).

</Accordion>

<Accordion title="Owner-only writes and admin">

read_when:

- Using /steer or /tell while an agent is already running

- Comparing /steer with /queue modes

- Deciding whether to steer the current run, a sub-agent, or an ACP session

- Deciding whether to steer the current run or an ACP session

title: "Steer"

sidebarTitle: "Steer"

---

## Sub-agents

Use `/subagents steer` when the target is a child run:

```text

/subagents steer 2 focus only on the API surface

```

Top-level `/steer` does not select a sub-agent by id or list index. It always

targets the current session's active run. See [Sub-agents](/tools/subagents) for

sub-agent ids, labels, and control commands.

Top-level `/steer` targets the current session's active run. Sub-agents report

back to their parent/requester session; `/subagents` is for visibility only.

## ACP sessions